Black Forest Labs Flux 3 Image To Video Draft

Black Forest Labs Flux 3 Image To Video Draft

Playground

Try it on WaveSpeedAI!

FLUX 3 Image-to-Video Draft quickly animates a required reference image into a draft clip with prompt-guided motion, optional synchronized audio, and flexible 5-20 second duration for rapid visual iteration.

Features

FLUX 3 Draft Image-to-Video quickly animates a required reference image into a motion preview. Use the image to anchor the subject, character, product, scene, or style, then test different actions and camera directions before creating a final-quality video.

Key Capabilities

  • Animate a reference image into a draft video.
  • Test subject motion, camera movement, scene atmosphere, and visual continuity quickly.
  • Optionally generate synchronized audio for early sound and storytelling tests.
  • Choose a duration from 5 to 20 seconds.
  • Support landscape, portrait, square, and cinematic aspect ratios.

Parameters

ParameterRequiredDescription
promptYesDescribe the desired action, motion, environment, camera movement, timing, mood, lighting, and style.
imageYesReference image used as the visual starting point. Supports PNG, JPEG, or WebP URLs.
aspect_ratioNoOutput aspect ratio. Options: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.
durationNoDraft video duration in seconds. Choose an integer from 5 to 20. Default: 5.
generate_audioNoGenerate synchronized audio for the draft video. Default: true.

How to Use

  1. Provide a clear reference image with the subject or composition you want to animate.
  2. Describe the motion, camera path, environment, and style change in the prompt.
  3. Choose an aspect ratio and duration for the draft preview.
  4. Enable generate_audio when you want to test matching ambience, effects, music, or dialogue.
  5. Review the motion and refine the prompt before moving to a final production workflow.

Prompting Tips

  • State what must remain consistent from the image and what should change through motion.
  • Use specific actions such as turning, walking, rotating, opening, flowing, or drifting.
  • Add camera language such as slow push-in, tracking shot, orbit, handheld movement, or fixed frame.
  • Start with a simple motion direction, then add more detail after the first draft is stable.

Pricing

Billing UnitPrice
Per second$0.06

Billing Rules

  • The billed duration is rounded up to the next whole second.
  • The minimum billed duration is 5 seconds.
  • The maximum billed duration is 20 seconds.
  • Audio generation does not add a separate charge in the current pricing formula.
  • Example: a 5-second draft costs $0.30.
  • Example: a 10-second draft costs $0.60.

Best Use Cases

  • Fast animation tests for portraits, products, and illustrations.
  • Character motion and pose exploration.
  • Product-video concept development.
  • Social content ideation and visual style testing.
  • Comparing alternative actions from the same reference image.

Notes

  • A reference image and prompt are both required.
  • Use a clear image with the subject visible and enough detail for motion planning.
  • Draft outputs are intended for exploration and iteration.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "aspect_ratio": "21:9",
  "duration": 5,
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/image-to-video-draft" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The text prompt describing the video you want to generate.
imagestringYes-URL of the image the video starts from (PNG, JPEG, or WebP)..
aspect_ratiostringNo-21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16The aspect ratio of the generated media.
durationintegerNo55 ~ 20Video length in seconds (5-20).
generate_audiobooleanNotrue-Whether to generate audio for the video.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.